Claude Canvas MCP

What is Claude Canvas MCP?

Claude Canvas MCP is a Model Context Protocol server that enables Claude to interact with Canvas LMS through the Canvas API. It provides tools for managing courses, announcements, assignments, students, files, and more. This server is designed for educators and administrators who use Canvas and want to automate workflows via Claude.

How to use Claude Canvas MCP?

Install dependencies with npm install, build the TypeScript project with npm run build, then configure environment variables in a .env file with your Canvas API token and domain. Finally, add the server to Claude Desktop’s configuration file (claude_desktop_config.json) under mcpServers, pointing to the built index.js and setting CANVAS_API_TOKEN and CANVAS_DOMAIN. Restart Claude Desktop to start using the tools.

Key features of Claude Canvas MCP

• List active courses and their details
• Retrieve course modules, pages, and content
• View assignments, quizzes, and discussions
• Access student enrollment information
• Post announcements and comments
• View submission details and grades
• Upload and download files
• Manage rubrics and grades

Use cases of Claude Canvas MCP

• Automatically list all active courses for a user
• Post an announcement to a course from a prompt
• View all student submissions for an assignment
• Upload a file to a course folder
• Retrieve detailed information about a specific course, module, or assignment

FAQ from Claude Canvas MCP

What are the prerequisites for running Claude Canvas MCP?

You need Node.js v16 or higher, a Canvas API token, a Canvas instance URL (defaults to http://canvas.docker/), and the Claude Desktop application.

How do I configure the server with my Canvas instance?

Set the CANVAS_API_TOKEN and CANVAS_DOMAIN environment variables in your .env file or in the env section of the Claude Desktop configuration.

Where does my Canvas data live?

Data stays in your Canvas instance; the server acts as a bridge via the Canvas API and does not store any data locally.

What transport does the server use?

The server runs as a subprocess of Claude Desktop via stdio, as defined by the command and args in the Claude Desktop configuration.

What authentication method is required?

The server uses a Canvas API token provided via the CANVAS_API_TOKEN environment variable.